mlsanityData to 7 Oct 2026

A Survey on Retrieval-Augmented Text Generation

arXiv 2202.01110 ↗First posted 2 Feb 2022cs.CLcited by 157

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and other generation tasks. Finally, it points out some important directions on top of recent methods to facilitate future research.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 46 of its 85 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

46 of 85 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  9. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  11. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  12. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
34 more
  1. 2021Internet-Augmented Dialogue Generationcited by 217
  2. 2020Nearest Neighbor Machine Translationcited by 209
  3. 2015A Neural Conversational Modelcited by 195
  4. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  5. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  6. 2018A Dataset for Document Grounded Conversationscited by 104
  7. 2020Pre-training via Paraphrasingcited by 92
  8. 2015Convolutional Neural Network Architectures for Matching Natural Language Sentencescited by 82
  9. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  10. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  11. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  12. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  13. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  14. 2021Adaptive Nearest Neighbor Machine Translationcited by 58
  15. 2018Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memorycited by 49
  16. 2020A Controllable Model of Grounded Response Generationcited by 49
  17. 2019Controllable Paraphrase Generation with a Syntactic Exemplarcited by 44
  18. 2018Response Generation by Context-aware Prototype Editingcited by 40
  19. 2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
  20. 2021Fast Nearest Neighbor Machine Translationcited by 37
  21. 2019Incremental Transformer with Deliberation Decoder for Document Grounded Conversationscited by 35
  22. 2019Non-Parametric Adaptation for Neural Machine Translationcited by 34
  23. 2019Conversing by Reading: Contentful Neural Conversation with On-demand Machine Readingcited by 32
  24. 2019Text Generation with Exemplar-based Adaptive Decodingcited by 28
  25. 2020Controlling Dialogue Generation with Semantic Exemplarscited by 25
  26. 2020Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memorycited by 22
  27. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  28. 2021Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translationcited by 20
  29. 2014An Information Retrieval Approach to Short Text Conversationcited by 18
  30. 2019A Hybrid Retrieval-Generation Neural Conversation Modelcited by 18
  31. 2016Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systemscited by 13
  32. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  33. 2016One Sentence One Model for Neural Machine Translationcited by 7
  34. 2019Learning to Reuse Translations: Guiding Neural Machine Translation with Examplescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 30; 2024: 69; 2025: 34; 2026: 9.

157 papers.

Sort:

By area:

  1. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  3. 2023Cognitive Architectures for Language Agentscited by 422
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  5. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  6. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 211
  7. 2024Corrective Retrieval Augmented Generationcited by 187
  8. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  9. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  10. 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
  11. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  12. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 101
38 more
  1. 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
  2. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  3. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  4. 2022SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentationcited by 82
  5. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  6. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  7. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  8. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  9. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  10. 2024"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Modelscited by 60
  11. 2024Agents in Software Engineering: Survey, Landscape, and Visioncited by 60
  12. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  13. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Frameworkcited by 47
  14. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 47
  15. 2024Octopus v2: On-device language model for super agentcited by 45
  16. 2024EPIC: Efficient Position-Independent Caching for Serving Large Language Modelscited by 45
  17. 2022Retrieval-based Controllable Molecule Generationcited by 44
  18. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  19. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  20. 2024Retrieval Augmented Time Series Forecastingcited by 40
  21. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  22. 2024With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generationcited by 36
  23. 2024From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injectioncited by 36
  24. 2024Block-Attention for Efficient Prefillingcited by 34
  25. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  26. 2023Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanismcited by 33
  27. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  28. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 30
  29. 2024DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentationcited by 30
  30. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29
  31. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  32. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defectscited by 27
  33. 2025Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systemscited by 27
  34. 2023RECAP: Retrieval-Augmented Audio Captioningcited by 26
  35. 2024Reinforcement Learning for Optimizing RAG for Domain Chatbotscited by 26
  36. 2023Copy Is All You Needcited by 25
  37. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  38. 2024Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selectioncited by 25

50 most cited of 157 All 157 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  2. 2024E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
  3. 2024Meta-prompting Optimized Retrieval-augmented Generation
  4. 2023Active Retrieval Augmented Generation
  5. 2024Evaluation of Retrieval-Augmented Generation: A Survey
  6. 2024R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
  7. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
  8. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices